SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography

Abstract

Early diagnosis of breast cancer unequivocally improves the survival rate of patients and is crucial for disease treatment. With the current developments in infrared imaging, breast screening using dynamic thermography seems to be a great complementary method for clinical breast examination (CBE) prior to mammography. In this study, we propose a sparse deep convolutional autoencoder model named SPAER to extract low-dimensional deep thermomics to aid breast cancer diagnosis. The model receives multichannel, low-rank, approximated thermal bases as input images. SPAER provides a solution for high-dimensional deep learning features and selects the predominant basis matrix using matrix factorization techniques. The model has been evaluated using five state-of-the-art matrix factorization methods and 208 thermal breast cancer screening cases. The best accuracy was for non-negative matrix factorization (NMF)-SPAER + Clinical and NMF-SPAER for maintaining thermal heterogeneity, leading to finding symptomatic cases with accuracies of 78.2% (74.3–82.5%) and 77.7% (70.9–82.1%), respectively. SPAER showed significant robustness when tested for additive Gaussian noise cases (3–20% noise), evaluated by the signal-to-noise ratio (SNR). The results suggest high performance of SPAER for preserveing thermal heterogeneity, and it can be used as a noninvasive in vivo tool aiding CBE in the early detection of breast cancer.

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

“…Similarly, our model exhibited considerable growth in model performance for classifying breast cancer patients from benign cases ( Figure 7 , and Table 2 ). The proposed model in this study follows the previously mentioned methodologies [ 43 ], to design models for generating deep radiomics with low dimensionality, thereby surpassing the possibility of overfitting in our model and the issue of the curse of dimensionality . The proposed model gave low-dimensional deep radiomics through its latent space projection, while instantaneously segmenting breast lesions in ultrasound images.…”

“…This model is motivated by SPAER [ 43 ] configuration with slight modifications toward segmentation and alleviating sparsity in the latent representation by taking away the additional penalty term from the model. Figure 1 and Figure 3 display the configuration of the proposed deep learning model.…”

“…The high dimensional radiomic data is addressed through two separated methodologies which interact by combining the outcome imaging biomarkers for the final decision-making unit, random forest. A deep neural network structure motivated by SPAER [ 43 ] proposed to reduce the dimensionality from 262,144 pixels to a 4 pixel-array biomarker. The second dimensionality reduction path involves conventional radiomics.…”

A Diagnostic Biomarker for Breast Cancer Screening via Hilbert Embedded Deep Low-Rank Matrix Approximation

“…The application of thermomics increased the dimensionality of the input thermal imaging and intensify the possibility of overfitting the random forest model, curse of dimensionality [28][29][30][31][32][33][34]. The Block-HSIC lasso reduced the dimensionality by removing the redundancy among the features by spanning thermomics to higher dimensional space using RBF Gaussian kernel and measuring HSIC lasso, which increases the robustness of feature selection versus outliers.…”

Dynamic Vascular Imaging Using Active Breast Thermography

“…We introduce a supplementary study of VWT in Appendix A . Yousefi et al [ 17 , 18 , 19 ] employed PCA in the dynamic data to preprocess vein data for further artificial intelligence (A.I.) interpretation.…”